Technologies

People on the autism spectrum and other neurodivergent people may experience sensory-rich environments as distressing, while teachers and care professionals must often identify and respond to environmental discomfort with limited objective information. This study reports the human-centered requirement elicitation, prototype development, and quantitative pilot evaluation of an environmental-monitoring system that relies on rule-based thresholds. Across three case-study settings, 125 stakeholder participations informed the development and design of a smart sensor system measuring sound, light, temperature, and air quality. The subsequent pre–post pilot study was conducted at four Austrian and Italian centers from February to June 2026. In total, 42 clients or pupils and 26 teachers or care professionals participated in the evaluation measures of the pilot study. Post-study acceptance was positive: overall meCUE user experience scores ranged from 4.88 to 4.94 on a seven-point scale, and AttrakDiff overall attractiveness averaged 1.21 (SD = 1.06) on a scale from −3 to +3. The results support the usability and perceived value of the prototype to maintain supportive environmental conditions.

Dual-layer bit-patterned magnetic recording (DL-BPMR) is a promising approach to extend areal-density scaling by exploiting the vertical dimension; however, reliable retrieval is challenged by the inherently weaker lower-layer readback and additional interference mechanisms, inter-symbol interference, inter-track interference, and inter-layer interference, that distort the mixed readback signal. This study presents a co-designed dual-layer BPMR scheme with an areal density of 2.0 to 6.0 Terabits per square inch (Tbits/in²), based on two complementary approaches. First, we vary the head–media spacing (HMS) to reduce the distance between the read head and the recording layers, especially the lower layer, strengthening the lower-layer contribution and making the mixed readback clearer and more reliable. Second, conditioned-HMS readback is processed using a combined-processing receiver tailored to a staggered (down-track-offset) dual-layer layout, where oversampling enables a unified one-dimensional sequence representation for dual-layer detection without enforcing early layer separation. To further improve detection efficiency, we also introduce a two-step minimum mean square error design that first determines a short monic generalized partial response target and then computes a minimum mean square error equalizer matched to the resulting readback, producing an equalized sequence suitable for soft-output sequence detection and low-density parity-check coded decoding. The simulation results indicated that reducing the head-media spacing improves readback separability (i.e., reliability) and that the proposed two-step combined-processing partial-response maximum-likelihood method achieves a consistently lower mean-squared error than conventional dual-layer processing across signal-to-noise ratios (SNRs). More importantly, in end-to-end bit-error-rate (BER) evaluation under electronic noise, e.g., the proposed dual-layer BPMR system delivers a clear reliability advantage over a single-layer BPMR baseline, achieving SNR gains of 4.2 dB at BER = 10⁻⁴ and 3.7 dB at BER = 10⁻⁵ in the favorable head-media spacing regime, thereby demonstrating robust high-density dual-layer retrieval beyond the single-layer baseline.

Cyanobacterial blooms threaten the water supply in regulated reservoirs, but the weekly early-warning skill and the usefulness of basin-scale water-quality gradients are not-well quantified. This study created a weekly bloom-risk framework for Jinyang Lake, South Korea, based on the probability of cyanobacteria exceeding 1000 cells/mL in the next 1–4 weeks. Weekly data from 16 stations (2011–2025) trained Deep Long Short-Term Memory (LSTM) and hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) classifiers (training 2011–2022, tuning 2023, independent testing 2024–2025; 48 weeks). The results of principal component analysis (PCA) indicated that the first two components accounted for 46.9–88.1% of the variance by variable, so no single station represented basin-wide conditions. At the 4-week horizon, the hybrid CNN-LSTM achieved F1 = 0.849 (95% CI: 0.74–0.93) and critical success index (CSI) = 0.738 at Naedong, and F1 = 0.758 (0.62–0.88) and CSI = 0.610 at Panmun, exceeding Random Forest (F1 = 0.58–0.62) and XGBoost (F1 = 0.55–0.58). At Naedong, the area under the curve (AUC) was 0.523, while, at Panmun, it was 0.768, due to the class-weighted training that resulted in probabilities being squeezed into a narrow range. PCA-derived features numerically increased the F1 score at Panmun by 0.020–0.041 (not statistically significant) and reduced the Naedong hybrid F1 score from 0.849 to 0.786. Platt scaling reduced hybrid-model Brier scores by 27–29% at both lake stations, improving the usability of the probabilities for operational decisions. The multi-week bloom-risk framework offers reservoir operators and municipal drinking-water systems probabilistic early-warning decision support for preventive action before critical bloom development.